{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T17:57:42Z","timestamp":1768499862348,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556786","type":"print"},{"value":"9789819556793","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5679-3_25","type":"book-chapter","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:42Z","timestamp":1768329402000},"page":"358-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["C3F: A Coarse-to-Fine Feature Fusion Approach for\u00a0Scene Script Identification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7753-0757","authenticated-orcid":false,"given":"Zhonghua","family":"Sun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6470-201X","authenticated-orcid":false,"given":"Yaowei","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1130-0468","authenticated-orcid":false,"given":"Kaisaier","family":"Tuerxun","sequence":"additional","affiliation":[]},{"given":"Alimjan","family":"Aysa","sequence":"additional","affiliation":[]},{"given":"Kurban","family":"Ubul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"25_CR1","first-page":"6546","volume":"5","author":"K Ubul","year":"2017","unstructured":"Ubul, K., Tursun, G., Aysa, A., Impedovo, D., Pirlo, G., Yibulayin, T.: Script identification of multi-script documents: a survey. IEEE Access 5, 6546\u20136559 (2017)","journal-title":"IEEE Access"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Sharma, N., Mandal, R., Sharma, R., et al.: Bag-of-visual words for word-wise video script identification: a study. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2015)","DOI":"10.1109\/IJCNN.2015.7280631"},{"key":"25_CR3","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR, 6105\u20136114 (2019)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"25_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108542","volume":"118","author":"Z Chao","year":"2022","unstructured":"Chao, Z., Duan, X., Jia, S., et al.: Medical image fusion via discrete stationary wavelet transform and an enhanced radial basis function neural network. Appl. Soft Comput. 118, 108542 (2022)","journal-title":"Appl. Soft Comput."},{"key":"25_CR6","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 1\u201311 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"23","key":"25_CR7","doi-asserted-by":"publisher","first-page":"62677","DOI":"10.1007\/s11042-023-17986-z","volume":"83","author":"F Peng","year":"2024","unstructured":"Peng, F., Ma, H., Liu, L., et al.: Adaptive feature fusion for scene text script identification. Multimedia Tools Appl. 83(23), 62677\u201362699 (2024)","journal-title":"Multimedia Tools Appl."},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"Pan, Z., Yang, Y., Ubul, K., et al.: Script identification in the wild with FFT-multi-grained mix attention transformer. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) ICDAR 2024. LNCS, vol .14805, pp. 104\u2013117. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70536-6_7","DOI":"10.1007\/978-3-031-70536-6_7"},{"key":"25_CR9","unstructured":"Ma, X., Dai, X., Yang, J., et al.: Efficient modulation for vision networks (2024). arXiv preprint arXiv:2403.19963"},{"issue":"4","key":"25_CR10","doi-asserted-by":"publisher","first-page":"5355","DOI":"10.1109\/TNNLS.2022.3204090","volume":"35","author":"H Du","year":"2022","unstructured":"Du, H., Wang, J., Liu, M., et al.: SwinPA-Net: swin transformer-based multiscale feature pyramid aggregation network for medical image segmentation. IEEE Trans. Neural Networks Learn. Syst. 35(4), 5355\u20135366 (2022)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"25_CR11","unstructured":"Zhang, T., Li, L., Zhou, Y., et al.: CAS-ViT: convolutional additive self-attention vision transformers for efficient mobile applications (2024). arXiv preprint arXiv:2408.03703"},{"issue":"5","key":"25_CR12","first-page":"4571","volume":"39","author":"M Lei","year":"2025","unstructured":"Lei, M., Wu, H., Lv, X., et al.: CondSeg: a general medical image segmentation framework via contrast-driven feature enhancement. J. Artif. Intell. Res. 39(5), 4571\u20134579 (2025)","journal-title":"J. Artif. Intell. Res."},{"key":"25_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-21074-8_11","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"M Bu\u0161ta","year":"2019","unstructured":"Bu\u0161ta, M., Patel, Y., Matas, J.: E2E-MLT - an unconstrained end-to-end method for multi-language scene text. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 127\u2013143. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_11"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1016\/j.patcog.2015.11.005","volume":"52","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: Script identification in the wild via discriminative convolutional neural network. Pattern Recogn. 52, 448\u2013458 (2016)","journal-title":"Pattern Recogn."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Sharma, N., Mandal, R., Sharma, R., et al.: ICDAR2015 competition on video script identification (CVSI 2015). In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1196\u20131200. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333950"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Nayef, N., Yin, F., Bizid, I., et al.: ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification - RRC-MLT. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1454\u20131459. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Mei, J., Dai, L., Shi, B., et al.: Scene text script identification with convolutional recurrent neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 4053\u20134058. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7900268"},{"key":"25_CR18","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.patcog.2017.01.032","volume":"67","author":"L Gomez","year":"2017","unstructured":"Gomez, L., Nicolaou, A., Karatzas, D.: Improving patch-based scene text script identification with ensembles of conjoined networks. Pattern Recogn. 67, 85\u201396 (2017)","journal-title":"Pattern Recogn."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Zdenek, J., Nakayama, H.: Bag of local convolutional triplets for script identification in scene text. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 369\u2013375. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.68"},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.patcog.2018.07.034","volume":"85","author":"A Konwer","year":"2019","unstructured":"Konwer, A., Bhunia, A.K., Bhunia, A.K., et al.: Script identification in natural scene image and video frames using an attention based convolutional-LSTM network. Pattern Recogn. 85, 172\u2013184 (2019)","journal-title":"Pattern Recogn."},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Cheng, C., Huang, Q., Bai, X., et al.: Patch aggregator for scene text script identification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1077\u20131083. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00175"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"52669","DOI":"10.1109\/ACCESS.2019.2911964","volume":"7","author":"L Lu","year":"2019","unstructured":"Lu, L., Yi, Y., Huang, F., et al.: Integrating local CNN and global CNN for script identification in natural scene images. IEEE Access 7, 52669\u201352679 (2019)","journal-title":"IEEE Access"},{"key":"25_CR23","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/j.neucom.2020.09.015","volume":"421","author":"M Ma","year":"2021","unstructured":"Ma, M., Wang, Q.F., Huang, S., et al.: Residual attention-based multi-scale script identification in scene text images. Neurocomputing 421, 222\u2013233 (2021)","journal-title":"Neurocomputing"},{"issue":"1","key":"25_CR24","first-page":"551","volume":"40","author":"L Lu","year":"2021","unstructured":"Lu, L., Wu, D., Tang, Z., et al.: Mining discriminative patches for script identification in natural scene images. J. Intell. Fuzzy Syst. 40(1), 551\u2013563 (2021)","journal-title":"J. Intell. Fuzzy Syst."},{"key":"25_CR25","doi-asserted-by":"publisher","unstructured":"Moharir, R., Prabhu, A.D., Moharana, S., Ramena, G., Munjal, R.S.: On-device spatial attention based sequence learning approach for scene text script identification. In: Raman, B., Murala, S., Chowdhury, A., Dhall, A., Goyal, P. (eds.) CVIP 2021. CCIS, vol. 1568, pp. 230\u2013242. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-11349-9_20","DOI":"10.1007\/978-3-031-11349-9_20"},{"key":"25_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104916","volume":"113","author":"K Yang","year":"2022","unstructured":"Yang, K., Yi, J., Chen, A., et al.: ConvPatchTrans: a script identification network with global and local semantics deeply integrated. Eng. Appl. Artif. Intell. 113, 104916 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.patrec.2023.04.015","volume":"171","author":"X Li","year":"2023","unstructured":"Li, X., Zhan, H., Shivakumara, P., et al.: SANet-SI: a new self-attention-network for script identification in scene images. Pattern Recogn. Lett. 171, 45\u201352 (2023)","journal-title":"Pattern Recogn. Lett."},{"issue":"7","key":"25_CR28","doi-asserted-by":"publisher","first-page":"4434","DOI":"10.3390\/app13074434","volume":"13","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., Mamat, H., Xu, X., et al.: FAS-Res2net: an improved res2net-based script identification method for natural scenes. Appl. Sci. 13(7), 4434 (2023)","journal-title":"Appl. Sci."},{"issue":"13","key":"25_CR29","doi-asserted-by":"publisher","first-page":"2837","DOI":"10.3390\/electronics12132837","volume":"12","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., Eli, E., Mamat, H., et al.: EA-ConvNext: an approach to script identification in natural scenes based on edge flow and coordinate attention. Electronics 12(13), 2837 (2023)","journal-title":"Electronics"},{"key":"25_CR30","doi-asserted-by":"publisher","unstructured":"Pan, Z., Yang, Y., Ubul, K., et al.: A new bottom-up path augmentation attention network for script identification in scene images. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) ICDAR 2024. LNCS, vol. 14808, pp. 227\u2013244. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70549-6_14","DOI":"10.1007\/978-3-031-70549-6_14"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5679-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:45Z","timestamp":1768329405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5679-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556786","9789819556793"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5679-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}